Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1866 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9461. Min Range: -5.9461
Max Act: 5.9461. Min Act: -0.1700
Data Index: 2416662 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9461. Min Range: -5.9461
Max Act: 5.8211. Min Act: -0.1700
Data Index: 5280777 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9461. Min Range: -5.9461
Max Act: 5.6649. Min Act: -0.1700
Data Index: 2257485 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9461. Min Range: -5.9461
Max Act: 5.6649. Min Act: -0.1700
Data Index: 7751734 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9461. Min Range: -5.9461
Max Act: 5.6649. Min Act: -0.1700
Data Index: 2639245 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9461. Min Range: -5.9461
Max Act: 5.6649. Min Act: -0.1700
Data Index: 8230280 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9461. Min Range: -5.9461
Max Act: 5.6649. Min Act: -0.1700
Data Index: 7217550 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9461. Min Range: -5.9461
Max Act: 5.6024. Min Act: -0.1700
Data Index: 398000 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9461. Min Range: -5.9461
Max Act: 5.6024. Min Act: -0.1700
Data Index: 3994036 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9461. Min Range: -5.9461
Max Act: 5.5711. Min Act: -0.1700
Data Index: 7842323 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9461. Min Range: -5.9461
Max Act: 5.6024. Min Act: -0.1700
Data Index: 1382898 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9461. Min Range: -5.9461
Max Act: 5.6024. Min Act: -0.1700
Data Index: 3864838 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9461. Min Range: -5.9461
Max Act: 5.5711. Min Act: -0.1700
Data Index: 7859533 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9461. Min Range: -5.9461
Max Act: 5.5711. Min Act: -0.1700
Data Index: 4828382 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9461. Min Range: -5.9461
Max Act: 5.5711. Min Act: -0.1700
Data Index: 6618953 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9461. Min Range: -5.9461
Max Act: 5.5711. Min Act: -0.1700
Data Index: 7748656 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9461. Min Range: -5.9461
Max Act: 5.5711. Min Act: -0.1700
Data Index: 8793163 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9461. Min Range: -5.9461
Max Act: 5.5711. Min Act: -0.1700
Data Index: 5280140 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9461. Min Range: -5.9461
Max Act: 5.5399. Min Act: -0.1700
Data Index: 3877774 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9461. Min Range: -5.9461
Max Act: 5.5399. Min Act: -0.1700
Data Index: 1419007 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #19